{"id":"W4409916786","doi":"10.1109/tse.2025.3565387","title":"Question Selection for Multimodal Code Search Synthesis Using Probabilistic Version Spaces","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Selection (genetic algorithm); Probabilistic logic; Modal; Programming language; Code (set theory); Theoretical computer science; Artificial intelligence; Set (abstract data type)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002418502,0.0001639273,0.0001466423,0.0003984609,0.0002451794,0.0001378755,0.0002878177,0.0001212382,0.00000335595],"category_scores_gemma":[0.0001445747,0.0001719308,0.00007921747,0.0006045286,0.00001664102,0.0004128578,0.000004150388,0.0002393043,0.000002193181],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003868357,"about_ca_system_score_gemma":0.00009627091,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000809941,"about_ca_topic_score_gemma":0.000009890844,"domain_scores_codex":[0.9990394,0.00003101381,0.0001614878,0.0003492482,0.0001726082,0.0002462903],"domain_scores_gemma":[0.9992193,0.0003439454,0.00002991206,0.0002110503,0.0001508621,0.0000449185],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004701831,0.0001320667,0.00003802775,0.000500376,0.00005329547,0.000002052668,0.0001633254,0.8952281,0.02496307,0.001788398,0.00003859603,0.07704568],"study_design_scores_gemma":[0.0001128288,0.00003625337,0.00001365512,0.0002973729,0.00002422583,0.000007013862,0.000004581032,0.7524911,0.2466107,0.0001993518,0.0000584481,0.0001444841],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01036298,0.0000985412,0.9870195,0.000076738,0.0004797507,0.0003531857,0.00001298913,0.001594553,0.000001768009],"genre_scores_gemma":[0.4623411,0.000002967261,0.5375101,0.00001216248,0.00001508336,0.00006779472,6.259104e-7,0.00001160928,0.00003855514],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4519781,"threshold_uncertainty_score":0.7011133,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01307841608488208,"score_gpt":0.2768731439809722,"score_spread":0.2637947278960901,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}